redai-infra/Relax

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

⭐ 578 ⑂ 141 Python Apache-2.0 · 2 天前推送

https://redai-infra.github.io/Relax

distributed-training grpo multi-agent multimodal reinforcement-learning rlhf post-training agentic-rl ray-serve

578

Watchers

0

贡献者

0

Commits

0

Releases

155

Open Issues

2 天前

最近推送

原文中文

暂无 README